From agent-platform-pro
Intelligent LLM provider selection based on task characteristics, cost-latency-quality optimization. Use when choosing the best AI provider for a task.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-platform-pro:provider-routerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Intelligently routes tasks to the optimal LLM provider based on task characteristics, cost constraints, latency requirements, and quality needs. Maintains a provider capability matrix, implements fallback chains for resilience, manages token budgets across providers, and monitors provider health. The routing decision is explainable — every choice comes with a "why this provider" justification.
Intelligently routes tasks to the optimal LLM provider based on task characteristics, cost constraints, latency requirements, and quality needs. Maintains a provider capability matrix, implements fallback chains for resilience, manages token budgets across providers, and monitors provider health. The routing decision is explainable — every choice comes with a "why this provider" justification.
cross-model-reviewer — Provider router selects which models participate in cross-model reviewmulti-agent-debate — Debate participants selected by provider routing logicserving-llms-vllm — Self-hosted models as additional routing targetsllama-cpp — Local inference as a routing option for low-latency/sensitive tasksnpx claudepluginhub haj1t/senior-dev-squad-skills --plugin agent-platform-proCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.